技術標籤：筆記pythonxml

序言

有些時候需要用到coco格式的資料訓練，但是labelimg標註的是VOC格式的檔案，需要轉換一些，原始檔案目錄格式為：

轉換方式一

直接將單個資料夾的xml轉換為json：

import xml.etree.ElementTree as ET
import os
import json

coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []

category_set = dict
 
()
image_set = set()

category_item_id = -1
image_id = 20180000000
annotation_id = 0


def addCatItem(name):
    global category_item_id
    category_item = dict()
    category_item['supercategory'] = 'none'
    category_item_id += 1
    category_item['id'] = category_item_id
    category_item['name'] = name
    coco[
 
'categories'].append(category_item)
    category_set[name] = category_item_id
    return category_item_id


def addImgItem(file_name, size):
    global image_id
    if file_name is None:
        raise Exception('Could not find filename tag in xml file.')
    if size['width'] is None:
        raise Exception(
 
'Could not find width tag in xml file.')
    if size['height'] is None:
        raise Exception('Could not find height tag in xml file.')
    image_id += 1
    image_item = dict()
    image_item['id'] = image_id
    image_item['file_name'] = file_name
    image_item['width'] = size['width']
    image_item['height'] = size['height']
    coco['images'].append(image_item)
    image_set.add(file_name)
    return image_id

def addAnnoItem(object_name, image_id, category_id, bbox):
    global annotation_id
    annotation_item = dict()
    annotation_item['segmentation'] = []
    seg = []
    # bbox[] is x,y,w,h
    # left_top
    seg.append(bbox[0])
    seg.append(bbox[1])
    # left_bottom
    seg.append(bbox[0])
    seg.append(bbox[1] + bbox[3])
    # right_bottom
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1] + bbox[3])
    # right_top
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1])

    annotation_item['segmentation'].append(seg)

    annotation_item['area'] = bbox[2] * bbox[3]
    annotation_item['iscrowd'] = 0
    annotation_item['ignore'] = 0
    annotation_item['image_id'] = image_id
    annotation_item['bbox'] = bbox
    annotation_item['category_id'] = category_id
    annotation_id += 1
    annotation_item['id'] = annotation_id
    coco['annotations'].append(annotation_item)


def _read_image_ids(image_sets_file):
    ids = []
    with open(image_sets_file) as f:
        for line in f:
            ids.append(line.rstrip())
    return ids

"""通過txt檔案生成"""

# split ='train' 'va' 'trainval' 'test'
def parseXmlFiles_by_txt(data_dir, json_save_path, split='train'):
    print("hello")
    labelfile = split + ".txt"
    image_sets_file = data_dir + "/ImageSets/Main/" + labelfile
    ids = _read_image_ids(image_sets_file)

    for _id in ids:
        xml_file = data_dir + f"/Annotations/{_id}.xml"

        bndbox = dict()
        size = dict()
        current_image_id = None
        current_category_id = None
        file_name = None
        size['width'] = None
        size['height'] = None
        size['depth'] = None

        tree = ET.parse(xml_file)
        root = tree.getroot()
        if root.tag != 'annotation':
            raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))

        # elem is <folder>, <filename>, <size>, <object>
        for elem in root:
            current_parent = elem.tag
            current_sub = None
            object_name = None

            if elem.tag == 'folder':
                continue

            if elem.tag == 'filename':
                file_name = elem.text
                if file_name in category_set:
                    raise Exception('file_name duplicated')

            # add img item only after parse <size> tag
            elif current_image_id is None and file_name is not None and size['width'] is not None:
                if file_name not in image_set:
                    current_image_id = addImgItem(file_name, size)
                    print('add image with {} and {}'.format(file_name, size))
                else:
                    raise Exception('duplicated image: {}'.format(file_name))
                    # subelem is <width>, <height>, <depth>, <name>, <bndbox>
            for subelem in elem:
                bndbox['xmin'] = None
                bndbox['xmax'] = None
                bndbox['ymin'] = None
                bndbox['ymax'] = None

                current_sub = subelem.tag
                if current_parent == 'object' and subelem.tag == 'name':
                    object_name = subelem.text
                    if object_name not in category_set:
                        current_category_id = addCatItem(object_name)
                    else:
                        current_category_id = category_set[object_name]

                elif current_parent == 'size':
                    if size[subelem.tag] is not None:
                        raise Exception('xml structure broken at size tag.')
                    size[subelem.tag] = int(subelem.text)

                # option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
                for option in subelem:
                    if current_sub == 'bndbox':
                        if bndbox[option.tag] is not None:
                            raise Exception('xml structure corrupted at bndbox tag.')
                        bndbox[option.tag] = int(option.text)

                # only after parse the <object> tag
                if bndbox['xmin'] is not None:
                    if object_name is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_image_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_category_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    bbox = []
                    # x
                    bbox.append(bndbox['xmin'])
                    # y
                    bbox.append(bndbox['ymin'])
                    # w
                    bbox.append(bndbox['xmax'] - bndbox['xmin'])
                    # h
                    bbox.append(bndbox['ymax'] - bndbox['ymin'])
                    print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
                                                                   bbox))
                    addAnnoItem(object_name, current_image_id, current_category_id, bbox)
    json.dump(coco, open(json_save_path, 'w'))

"""直接從xml資料夾中生成"""

def parseXmlFiles(xml_path, json_save_path):
    for f in os.listdir(xml_path):
        if not f.endswith('.xml'):
            continue

        bndbox = dict()
        size = dict()
        current_image_id = None
        current_category_id = None
        file_name = None
        size['width'] = None
        size['height'] = None
        size['depth'] = None

        xml_file = os.path.join(xml_path, f)
        print(xml_file)

        tree = ET.parse(xml_file)
        root = tree.getroot()
        if root.tag != 'annotation':
            raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))

        # elem is <folder>, <filename>, <size>, <object>
        for elem in root:
            current_parent = elem.tag
            current_sub = None
            object_name = None

            if elem.tag == 'folder':
                continue

            if elem.tag == 'filename':
                file_name = elem.text
                if file_name in category_set:
                    raise Exception('file_name duplicated')

            # add img item only after parse <size> tag
            elif current_image_id is None and file_name is not None and size['width'] is not None:
                if file_name not in image_set:
                    current_image_id = addImgItem(file_name, size)
                    print('add image with {} and {}'.format(file_name, size))
                else:
                    raise Exception('duplicated image: {}'.format(file_name))
                    # subelem is <width>, <height>, <depth>, <name>, <bndbox>
            for subelem in elem:
                bndbox['xmin'] = None
                bndbox['xmax'] = None
                bndbox['ymin'] = None
                bndbox['ymax'] = None

                current_sub = subelem.tag
                if current_parent == 'object' and subelem.tag == 'name':
                    object_name = subelem.text
                    if object_name not in category_set:
                        current_category_id = addCatItem(object_name)
                    else:
                        current_category_id = category_set[object_name]

                elif current_parent == 'size':
                    if size[subelem.tag] is not None:
                        raise Exception('xml structure broken at size tag.')
                    size[subelem.tag] = int(subelem.text)

                # option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
                for option in subelem:
                    if current_sub == 'bndbox':
                        if bndbox[option.tag] is not None:
                            raise Exception('xml structure corrupted at bndbox tag.')
                        bndbox[option.tag] = int(option.text)

                # only after parse the <object> tag
                if bndbox['xmin'] is not None:
                    if object_name is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_image_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_category_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    bbox = []
                    # x
                    bbox.append(bndbox['xmin'])
                    # y
                    bbox.append(bndbox['ymin'])
                    # w
                    bbox.append(bndbox['xmax'] - bndbox['xmin'])
                    # h
                    bbox.append(bndbox['ymax'] - bndbox['ymin'])
                    print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
                                                                   bbox))
                    addAnnoItem(object_name, current_image_id, current_category_id, bbox)
    json.dump(coco, open(json_save_path, 'w'))


if __name__ == '__main__':
    # 通過txt檔案生成
    # voc_data_dir="E:/VOCdevkit/VOC2007"
    # json_save_path="E:/VOCdevkit/voc2007trainval.json"
    # parseXmlFiles_by_txt(voc_data_dir,json_save_path,"trainval")

    # 通過資料夾生成
    ann_path = r"H:\VOC_COCO\voc_mini\Annotations"
    json_save_path = r"H:\VOC_COCO\train.json"
    parseXmlFiles(ann_path, json_save_path)

轉換方式二

轉換時自動劃分train和val，執行後得到：

# -*- coding=utf-8 -*-
#!/usr/bin/python

import sys
import os
import shutil
import numpy as np
import json
import xml.etree.ElementTree as ET

# 檢測框的ID起始值
START_BOUNDING_BOX_ID = 1
# 類別列表無必要預先建立，程式中會根據所有影象中包含的ID來建立並更新
PRE_DEFINE_CATEGORIES = {}
# If necessary, pre-define category and its id
#  PRE_DEFINE_CATEGORIES = {"aeroplane": 1, "bicycle": 2, "bird": 3, "boat": 4,
                         #  "bottle":5, "bus": 6, "car": 7, "cat": 8, "chair": 9,
                         #  "cow": 10, "diningtable": 11, "dog": 12, "horse": 13,
                         #  "motorbike": 14, "person": 15, "pottedplant": 16,
                         #  "sheep": 17, "sofa": 18, "train": 19, "tvmonitor": 20}


def get(root, name):
    vars = root.findall(name)
    return vars


def get_and_check(root, name, length):
    vars = root.findall(name)
    if len(vars) == 0:
        raise NotImplementedError('Can not find %s in %s.'%(name, root.tag))
    if length > 0 and len(vars) != length:
        raise NotImplementedError('The size of %s is supposed to be %d, but is %d.'%(name, length, len(vars)))
    if length == 1:
        vars = vars[0]
    return vars


# 得到圖片唯一標識號
def get_filename_as_int(filename):
    try:
        filename = os.path.splitext(filename)[0]
        print(filename)
        return int(filename)
    except:
        raise NotImplementedError('Filename %s is supposed to be an integer.'%(filename))


def convert(xml_list, xml_dir, json_file):
    '''
    :param xml_list: 需要轉換的XML檔案列表
    :param xml_dir: XML的儲存資料夾
    :param json_file: 匯出json檔案的路徑
    :return: None
    '''
    list_fp = xml_list
    # 標註基本結構
    json_dict = {"images":[],
                 "type": "instances",
                 "annotations": [],
                 "categories": []}
    categories = PRE_DEFINE_CATEGORIES
    bnd_id = START_BOUNDING_BOX_ID
    for line in list_fp:
        line = line.strip()
        print("buddy~ Processing {}".format(line))
        # 解析XML
        xml_f = os.path.join(xml_dir, line)
        tree = ET.parse(xml_f)
        root = tree.getroot()
        path = get(root, 'path')
        # 取出圖片名字
        if len(path) == 1:
            filename = os.path.basename(path[0].text)
        elif len(path) == 0:
            filename = get_and_check(root, 'filename', 1).text
        else:
            raise NotImplementedError('%d paths found in %s'%(len(path), line))
        ## The filename must be a number
        image_id = get_filename_as_int(filename)  # 圖片ID
        size = get_and_check(root, 'size', 1)
        # 圖片的基本資訊
        width = int(get_and_check(size, 'width', 1).text)
        height = int(get_and_check(size, 'height', 1).text)
        image = {'file_name': filename,
                 'height': height,
                 'width': width,
                 'id':image_id}
        json_dict['images'].append(image)
        ## Cruuently we do not support segmentation
        #  segmented = get_and_check(root, 'segmented', 1).text
        #  assert segmented == '0'
        # 處理每個標註的檢測框
        for obj in get(root, 'object'):
            # 取出檢測框類別名稱
            category = get_and_check(obj, 'name', 1).text
            # 更新類別ID字典
            if category not in categories:
                new_id = len(categories)
                categories[category] = new_id
            category_id = categories[category]
            bndbox = get_and_check(obj, 'bndbox', 1)
            xmin = int(float(get_and_check(bndbox, 'xmin', 1).text)) - 1
            ymin = int(float(get_and_check(bndbox, 'ymin', 1).text))- 1
            xmax = int(float(get_and_check(bndbox, 'xmax', 1).text))
            ymax = int(float(get_and_check(bndbox, 'ymax', 1).text))
            assert(xmax > xmin)
            assert(ymax > ymin)
            o_width = abs(xmax - xmin)
            o_height = abs(ymax - ymin)
            annotation = dict()
            annotation['area'] = o_width*o_height
            annotation['iscrowd'] = 0
            annotation['image_id'] = image_id
            annotation['bbox'] = [xmin, ymin, o_width, o_height]
            annotation['category_id'] = category_id
            annotation['id'] = bnd_id
            annotation['ignore'] = 0
            # 設定分割資料，點的順序為逆時針方向
            annotation['segmentation'] = [[xmin,ymin,xmin,ymax,xmax,ymax,xmax,ymin]]

            json_dict['annotations'].append(annotation)
            bnd_id = bnd_id + 1

    # 寫入類別ID字典
    for cate, cid in categories.items():
        cat = {'supercategory': 'none', 'id': cid, 'name': cate}
        json_dict['categories'].append(cat)
    # 匯出到json
    json_fp = open(json_file, 'w')
    json_str = json.dumps(json_dict)
    json_fp.write(json_str)
    json_fp.close()


if __name__ == '__main__':
    root_path = r"H:\VOC_COCO\voc_mini"        # 資料集路徑
    xml_dir = os.path.join(root_path, 'Annotations')       # xml路徑

    xml_labels = os.listdir(os.path.join(root_path, 'Annotations'))           # xml檔名
    np.random.shuffle(xml_labels)       # 隨機打亂
    split_point = int(len(xml_labels)/10)         # 總數分為10份

    # validation data
    xml_list = xml_labels[0:split_point]           # 驗證集
    json_file = './instances_val2014.json'       # 驗證集json名
    convert(xml_list, xml_dir, json_file)
    for xml_file in xml_list:
        img_name = xml_file[:-4] + '.jpg'
        shutil.copy(os.path.join(root_path, 'JPEGImages', img_name),
                    os.path.join(root_path, 'val2014', img_name))
    # train data
    xml_list = xml_labels[split_point:]      # 訓練集
    json_file = './instances_train2014.json'      # 訓練集json名
    convert(xml_list, xml_dir, json_file)
    for xml_file in xml_list:
        img_name = xml_file[:-4] + '.jpg'
        shutil.copy(os.path.join(root_path, 'JPEGImages', img_name),
                    os.path.join(root_path, 'train2014', img_name))